Kon is a minimal coding agent (and also a highly opinionated one)
☆343Aug 1, 2026Updated last week
Alternatives and similar repositories for kon
Users that are interested in kon are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Stop degrading your model's reasoning. A minimal, zero-config AI coding agent. Enforced ephemeral subagents keep context pure. From tiny …☆403Aug 4, 2026Updated last week
- ☆16Dec 16, 2024Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆11Jul 22, 2023Updated 3 years ago
- ☆43Aug 1, 2026Updated last week
- llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.☆263Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A simple no-install web UI for Ollama and OAI-Compatible APIs!☆31Jan 30, 2025Updated last year
- llama-swap + a minimal ollama compatible api☆61May 26, 2026Updated 2 months ago
- Chatons is a desktop AI workspace for coding and project workflows: it lets you chat with multiple AI providers, pick scoped or full mod…☆18May 27, 2026Updated 2 months ago
- ☆24Jan 22, 2025Updated last year
- Code for boomerang distillation enables zero-shot model size interpolation.☆22Jul 10, 2026Updated last month
- Prompt Jinja2 templates for LLMs☆36Jul 9, 2025Updated last year
- ☆16Oct 28, 2025Updated 9 months ago
- ☆99Mar 28, 2026Updated 4 months ago
- entropix style sampling + GUI☆27Oct 30, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Open-source framework for superagents.☆92Updated this week
- an auto-sleeping and -waking framework around llama.cpp☆13Feb 8, 2025Updated last year
- Customizable implementation of the self-instruct paper.☆1,051Mar 7, 2024Updated 2 years ago
- LLM fine-tuning and eval☆344Mar 21, 2024Updated 2 years ago
- A plugin for Oobabooga TextUI that allows you to search multiple search engines. Initially we're using Google API or DuckDuckGo.☆18Jun 4, 2023Updated 3 years ago
- Autonomous, agentic, creative story writing system that incorporates stored embeddings and Knowledge Graphs.☆108Feb 16, 2026Updated 5 months ago
- A tool that can be used to measure the sequential performance of any OpenAI-compatible LLM API☆25Aug 1, 2024Updated 2 years ago
- ⛔ DEPRECATED -- use flash-head instead (pip install flash-head)☆29Apr 10, 2026Updated 4 months ago
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆1,298Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆10Jun 30, 2022Updated 4 years ago
- Fine-tuning LLMs using QLoRA☆267Jun 21, 2026Updated last month
- Produce your own Dynamic 3.0 Quants and achieve optimum accuracy & SOTA quantization performance! Input a target size and the toolchain w…☆148Aug 1, 2026Updated last week
- Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on differe…☆88Aug 4, 2026Updated last week
- Spec-driven iterative development companion CLI for OpenCode.☆17Jun 7, 2026Updated 2 months ago
- Lightweight Llama 3 8B Inference Engine in CUDA C☆52Mar 21, 2025Updated last year
- Official code for ACL 2023 (short, findings) paper "Recursion of Thought: A Divide and Conquer Approach to Multi-Context Reasoning with L…☆45Jun 13, 2023Updated 3 years ago
- The fingerprinting library for Rust☆15Mar 30, 2026Updated 4 months ago
- Run autoresearch on any NVIDIA GPUs (Works on 2-4GB+ Cards)☆25Mar 22, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ik_llama.cpp's Thireus fork with release builds for macOS/Windows/Ubuntu CPU, Vulkan and CUDA☆167Updated this week
- interactive semantic search demo using Qwen3-0.6B-Embedding in your browser☆60Feb 25, 2026Updated 5 months ago
- Code for Papeg.ai☆228Jan 5, 2025Updated last year
- AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.☆2,004Updated this week
- RetroChat is a powerful command-line interface for interacting with various AI language models. It provides a seamless experience for eng…☆86Jul 13, 2025Updated last year
- Mixed-vendor GPU inference cluster manager with speculative decoding☆31Jul 2, 2026Updated last month
- Experimental sampler to make LLMs more creative☆31Aug 2, 2023Updated 3 years ago